What are some of the methods to minimize the monitor load on a Red Hat Ceph Storage cluster during heavy OSD rebalance operations?

Solution Verified - Updated -

Issue

  • What are some of the methods to minimise the monitor load on a Red Hat Ceph Storage cluster during heavy OSD rebalance operations?

  • What are the best practices for minimising Ceph Monitor load during heavy OSD rebalancing operations induced by a large ceph osd reweight command or by a major CRUSH Map update or by a massive addition of OSDs in a large cluster.

Environment

In large Ceph clusters, the number of OSDs present together with a high number of Placemenet Groups is naturally high and this induces an augmentation of the size of the different maps the cluster and the Monitors in partcular have to manage.

This leads to a situation where having an OSD being busy performing backfill or recovery operations can appear as unresponsive to peer OSDs and generate bursts of cluster MAP propagation within the cluster.

Subscriber exclusive content

A Red Hat subscription provides unlimited access to our knowledgebase of over 48,000 articles and solutions.

Current Customers and Partners

Log in for full access

Log In
Close

Welcome! Check out the Getting Started with Red Hat page for quick tours and guides for common tasks.